first commit

Invoice_parser/FITZ_250_450data/meta.json

@@ -0,0 +1,36 @@
+{
+  "lang":"en",
+  "name":"model",
+  "version":"0.0.0",
+  "spacy_version":">=2.3.5",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"1d4b1dea2",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":"spacy_pretrained_vectors"
+  },
+  "pipeline":[
+    "ner"
+  ],
+  "factories":{
+    "ner":"ner"
+  },
+  "labels":{
+    "ner":[
+      "Bank Account No",
+      "Bank Name",
+      "Due Date",
+      "Grand Total",
+      "Invoice Date",
+      "Invoice No",
+      "RTGS/IFSC Code",
+      "Round Off"
+    ]
+  }
+}

Invoice_parser/FITZ_250_450data/ner/cfg

@@ -0,0 +1,18 @@
+{
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":1.0,
+  "cnn_maxout_pieces":3,
+  "nr_feature_tokens":6,
+  "nr_class":34,
+  "hidden_depth":1,
+  "token_vector_width":96,
+  "hidden_width":64,
+  "maxout_pieces":2,
+  "pretrained_vectors":null,
+  "bilstm_depth":0,
+  "self_attn_depth":0,
+  "conv_depth":4,
+  "conv_window":1,
+  "embed_size":2000
+}

Invoice_parser/FITZ_250_450data/ner/moves

@@ -0,0 +1 @@
+�¥movesÚP{"0":{},"1":{"Invoice No":-1,"Invoice Date":-2,"Grand Total":-3,"Bank Name":-4,"Bank Account No":-5,"RTGS/IFSC Code":-6,"Due Date":-7,"Round Off":-8},"2":{"Invoice No":-1,"Invoice Date":-2,"Grand Total":-3,"Bank Name":-4,"Bank Account No":-5,"RTGS/IFSC Code":-6,"Due Date":-7,"Round Off":-8},"3":{"Invoice No":-1,"Invoice Date":-2,"Grand Total":-3,"Bank Name":-4,"Bank Account No":-5,"RTGS/IFSC Code":-6,"Due Date":-7,"Round Off":-8},"4":{"":1,"Invoice No":-1,"Invoice Date":-2,"Grand Total":-3,"Bank Name":-4,"Bank Account No":-5,"RTGS/IFSC Code":-6,"Due Date":-7,"Round Off":-8},"5":{"":1}}

Invoice_parser/FITZ_250_450data/vocab/key2row

@@ -0,0 +1 @@
+�

Invoice_parser/FITZ_250_450data/vocab/lookups.bin

@@ -0,0 +1 @@
+�«lexeme_norm€

Invoice_parser/Invoice.csv

@@ -0,0 +1,48 @@
+Key,Values
+SELLER NAME,Seller : SHREE TRADING CORPORATION
+SELLER ADDRESS,"6 & 7 Shree Sita Gaushala , Paharganj, Ajmer, Rajasthan - 305001"
+SELLER PH,Phone: 9610566688
+SELLER EMAIL,Email : stc.jaipur@gmail.com
+SELLER GST,GST No. : 08AAVPM5307P1ZV
+SELLER PAN,PAN No. : AAVPM5307P
+BUYER NAME,Buyer : Gurukripa Automobiles
+BUYER ADDRESS,"Ajmer Front Of Central Jail, Jaipur Road, Ajmer, 305001"
+BUYER GST,GST No. :Un Registered
+INVOICE NO,Invoice No. : AJM21-22/XM00444
+INVOICE DATE,Date : 06 Aug 2021
+SHIP TO,"Ship to :  , ,  "
+BUYER GST,GST No. :Un Registered
+SHIP TO CONTACT,"Contact: Sunil,8955050479"
+DESTINATION,Destination Terms
+SI,1
+HSN,27101980
+PRODUCT,MOBIL SUPER HP 10W-30 CTN 4X4L:IN-     
+PACK SIZE,1
+QUANTITY,16.00 LTR
+RATE,222.88
+DISC,160
+TAX %,9%|9%
+AMOUNT,3406.1
+SI,2
+HSN,27101980
+PRODUCT,MOBIL SUPER MGDO 15W-40 CTN 4X3.5L:IN-     
+PACK SIZE,6
+QUANTITY,84.00 LTR
+RATE,220.58
+DISC,2100
+TAX %,9%|9%
+AMOUNT,16428.8
+TOTAL PACKS & QUANTITY,Total Quantity 7.00 100.00
+ASSESSABLE AMOUNT,Assessable Amount 19834.90
+AMOUNT IN WORDS,Amount in words : Rupees Twenty Three Thousand Four Hundred Five only
+PAYMENT ON OR BEFORE,Payment on or before Save To pay
+OUTPUT SGST,Output SGST  
+OUTPUT CGST,1785.14 Output CGST  
+DISC,1785.14
+ROUND OFF,Round off -0.18
+RTS POINTS EARNED,RTS Points earned: 1200.00
+OVERALL RTS POINTS,Overall RTS Points: 1758.00
+GRAND TOTAL,Grand Total 23405.00
+OUR BANK DETAILS,Our Bank Details : Kotak Mahindra Bank
+BANK A/C NO,Bank A/c No. : 1412405384
+RTGS/IFSC,RTGS / IFSC Code : KKBK0003540

Invoice_parser/final.csv

@@ -0,0 +1,48 @@
+Key,Values
+SELLERNAME,Seller : SHREE TRADING CORPORATION
+SELLERADDRESS,"6 & 7 Shree Sita Gaushala , Paharganj, Ajmer, Rajasthan - 305001"
+SELLERPH,Phone: 9610566688
+SELLEREMAIL,Email : stc.jaipur@gmail.com
+SELLERGST,GST No. : 08AAVPM5307P1ZV
+SELLERPAN,PAN No. : AAVPM5307P
+BUYERNAME,Buyer : Gurukripa Automobiles
+BUYERADDRESS,"Ajmer Front Of Central Jail, Jaipur Road, Ajmer, 305001"
+BUYERGST,GST No. :Un Registered
+INVOICENO,Invoice No. : AJM21-22/XM00444
+INVOICEDATE,Date : 06 Aug 2021
+SHIPTO,"Ship to :  , ,  "
+BUYERGST,GST No. :Un Registered
+SHIPTOCONTACT,"Contact: Sunil,8955050479"
+DESTINATION,Destination Terms
+SI,1
+HSN,27101980
+PRODUCT,MOBIL SUPER HP 10W-30 CTN 4X4L:IN-     
+PACKSIZE,1.00
+QUANTITY,16.00 LTR
+RATE,222.88
+DISC,160.000
+TAX%,9%|9%
+AMOUNT,3406.10
+SI,2
+HSN,27101980
+PRODUCT,MOBIL SUPER MGDO 15W-40 CTN 4X3.5L:IN-     
+PACKSIZE,6.00
+QUANTITY,84.00 LTR
+RATE,220.58
+DISC,2100.000
+TAX%,9%|9%
+AMOUNT,16428.80
+TOTALPACKS&QUANTITY,Total Quantity 7.00 100.00
+ASSESSABLEAMOUNT,Assessable Amount 19834.90
+AMOUNTINWORDS,Amount in words : Rupees Twenty Three Thousand Four Hundred Five only
+PAYMENTONORBEFORE,Payment on or before Save To pay
+OUTPUTSGST,Output SGST  
+OUTPUTCGST,1785.14 Output CGST  
+DISC,1785.14
+ROUNDOFF,Round off -0.18
+RTSPOINTSEARNED,RTS Points earned: 1200.00
+OVERALLRTSPOINTS,Overall RTS Points: 1758.00
+GRANDTOTAL,Grand Total 23405.00
+OURBANKDETAILS,Our Bank Details : Kotak Mahindra Bank
+BANKACNO,Bank A/c No. : 1412405384
+RTGSIFSC,RTGS / IFSC Code : KKBK0003540

Invoice_parser/finalwithcolen.csv

@@ -0,0 +1,20 @@
+Key
+SELLERNAME
+SELLERPH
+SELLEREMAIL
+SELLERGST
+SELLERPAN
+BUYERNAME
+BUYERGST
+BUYERPAN
+INVOICENO
+INVOICEDATE
+PONO
+SHIPTO
+SHIPTOGST
+SHIPTOCONTACT
+DISC
+OURBANKDETAILS
+BANKACNO
+RTGSIFSC
+AMOUNTINWORDS

Invoice_parser/finalwithoutcolen.csv

@@ -0,0 +1,30 @@
+Key
+SELLERADDRESS
+BUYERADDRESS
+DESTINATION
+SI
+HSN
+PRODUCT
+PACKSIZE
+QUANTITY
+RATE
+DISC
+TAX%
+AMOUNT
+SI
+HSN
+PRODUCT
+PACKSIZE
+QUANTITY
+RATE
+DISC
+TAX%
+AMOUNT
+TOTALPACKS&QUANTITY
+PAYMENTONORBEFORE
+PAYMENTTYPE
+OUTPUTSGST
+OUTPUTCGST
+ROUNDOFF
+GRANDTOTAL
+ASSESSABLEAMOUNT

Invoice_parser/firstjson.json

@@ -0,0 +1 @@
+{"0":{"SELLERNAME":"SHREE TRADING CORPORATION","SELLERADDRESS":"6 & 7 Shree Sita Gaushala , Paharganj, Ajmer, Rajasthan - 305001","SELLERPH":9610566688,"SELLEREMAIL":"stc.jaipur@gmail.com","SELLERGST":"08AAVPM5307P1ZV","SELLERPAN":"AAVPM5307P","BUYERNAME":"Gurukripa Automobiles","BUYERADDRESS":"Ajmer Front Of Central Jail, Jaipur Road, Ajmer, 305001","BUYERGST":"Un Registered","INVOICENO":"AJM21-22\/XM00444","INVOICEDATE":"06 Aug 2021","SHIPTO":", ,","SHIPTOCONTACT":"Sunil,8955050479","DESTINATION":"Destination Terms","TOTALPACKS&QUANTITY":null,"ASSESSABLEAMOUNT":null,"AMOUNTINWORDS":"Rupees Twenty Three Thousand Four Hundred Five only","PAYMENTONORBEFORE":null,"OUTPUTSGST":null,"OUTPUTCGST":null,"ROUNDOFF":null,"RTSPOINTSEARNED":null,"OVERALLRTSPOINTS":null,"GRANDTOTAL":null,"OURBANKDETAILS":"Kotak Mahindra Bank","BANKACNO":1412405384,"RTGSIFSC":"KKBK0003540"}}

Invoice_parser/invoice.multiprocessing.py

@@ -0,0 +1,427 @@
+afrom flask import Flask, render_template, send_file, request, redirect, Response
+import spacy
+import os
+import shutil
+import pytesseract
+
+import requests
+
+import time
+import multiprocessing
+from PIL import Image
+from functools import partial
+
+app = Flask(__name__)
+nlp_model1 = spacy.load("p")
+app.config["IMAGE_UPLOADS"] = "/home/ubuntu/AI/InvoiceParser/upload_invoice"
+
+
+@app.route("/", methods=["GET"])
+def home():
+    return render_template("invoice.html")
+
+
+# @app.route("/upload_invoice", methods=["GET", "POST"])
+def predict(url_list):
+    # if request.method == "POST":
+
+    #     if request.files:
+
+    #         image = request.files["image"]
+    #         try:
+    #             image.save(os.path.join(app.config["IMAGE_UPLOADS"], image.filename))
+    #         except IsADirectoryError:
+    #             return render_template("invoice.html")
+    #         # image.save(os.path.join(
+    #         #     app1.config["IMAGE_UPLOADS"], image.filename))
+
+    #         print("Image saved in Invoice")
+
+    #         return redirect(request.url)
+    Dataset = request.get_json()
+    # print(Dataset)
+    a = url_list
+    x = a['FileData']
+    # print(x)
+    y = a['FileName']
+    z = a['FileType']
+    name = y + '.' + z
+    print(name)
+    # print(y)
+    # image = y.split("/")
+    # filename=image[-1]
+
+    # print(x)
+    img_data = x.encode()
+
+    import base64
+    with open('/home/ubuntu/AI/InvoiceParser/upload_invoice/' + name, "wb") as fh:
+        fh.write(base64.decodebytes(img_data))
+
+    # Renaming file name
+    # os.chdir("/home/ubuntu/AI/InvoiceParser/upload_invoice/")
+    # print(os.getcwd())
+    #
+    # for count, f in enumerate(os.listdir()):
+    #     f_name, f_ext = os.path.splitext(f)
+    #     f_name = "" + str(count)
+    #
+    #     new_name = f"{f_name}{f_ext}"
+    #     os.rename(f, new_name)
+    import glob
+    ts = 0
+    for file_name in glob.glob("/home/ubuntu/AI/InvoiceParser/upload_invoice/*"):
+        fts = os.path.getmtime(file_name)
+        if fts > ts:
+            ts = fts
+            found = file_name
+    print(found)
+
+    s = "/home/ubuntu/AI/InvoiceParser/upload_invoice"
+    s = os.listdir(s)
+    for file in s:
+        if file.endswith(".jpg"):
+            fname = (found)
+        elif file.endswith(".png"):
+            fname = (found)
+        elif file.endswith(".pdf"):
+            fname = (found)
+        elif file.endswith(".jpeg"):
+            fname = (found)
+        elif file.endswith(".JPEG"):
+            fname = (found)
+
+    def img_to_pdf():  # png to editable pdf conversion
+        pdf = pytesseract.image_to_pdf_or_hocr(fname, extension="pdf")
+        with open(
+                "/home/ubuntu/AI/InvoiceParser/upload_invoice/demo.pdf",
+                "w+b",
+        ) as f:
+            f.write(pdf)
+
+    if fname.endswith(".pdf"):
+        print()
+    else:
+        img_to_pdf()
+        fname = "/home/ubuntu/AI/InvoiceParser/upload_invoice/demo.pdf"
+
+    sourcepath = "/home/ubuntu/AI/InvoiceParser/upload_invoice"
+    sourcefiles = os.listdir(sourcepath)
+    destinationpath = "/home/ubuntu/AI/InvoiceParser/uploads"
+    for file in sourcefiles:
+        if file.endswith(".pdf"):
+            shutil.copy2(
+                os.path.join(sourcepath, file), os.path.join(destinationpath, file)
+            )
+    os.chdir("/home/ubuntu/AI/InvoiceParser/uploads")
+    print(os.getcwd())
+    print("file name conerted to o.pdf")
+    for count, f in enumerate(os.listdir()):
+        f_name, f_ext = os.path.splitext(f)
+        f_name = "" + str(count)
+        new_name = f"{f_name}{f_ext}"
+        os.rename(f, new_name)
+
+        import spacy
+        import sys
+        import fitz
+
+        fname = "/home/ubuntu/AI/InvoiceParser/uploads/0.pdf"
+        doc = fitz.open(fname)
+        text = ""
+        for page in doc:
+            text = text + str(page.get_text())
+
+        fitz = " ".join(text.split("\n"))
+        # print(fitz)
+
+        import pandas as pd
+
+        doc = nlp_model1(fitz)
+        k = []
+        l = []
+        for ent in doc.ents:
+            # print(f"{ent.label_.upper():{30}}- {ent.text}")
+            k.append(ent.label_.upper())
+            l.append(ent.text)
+
+        columns = k
+        rows = [l]
+        data = pd.DataFrame(rows, columns=columns)
+        df = data
+
+        df = data.T
+
+        df.to_csv("/home/ubuntu/AI/InvoiceParser/Invoice.csv")
+
+        import pandas as pd
+        df = pd.read_csv("/home/ubuntu/AI/InvoiceParser/Invoice.csv")
+        # df.head()
+        # df = df.T
+        # new_header = df.iloc[0]  # grab the first row for the header
+        # df = df[1:]  # take the data less the header row
+        # df.columns = new_header
+
+        # def df_column_uniquify(df):
+        #     df_columns = df.columns
+        #     new_columns = []
+        #     for item in df_columns:
+        #         counter = 0
+        #         newitem = item
+        #         while newitem in new_columns:
+        #             counter += 1
+        #             newitem = "{}_{}".format(item, counter)
+        #         new_columns.append(newitem)
+        #     df.columns = new_columns
+        #     return df.T
+
+        # df = df_column_uniquify(df)
+        # # df=df.T
+        # df.to_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        #df = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        df.rename({df.columns[-2]: 'Key'}, axis=1, inplace=True)
+        df.rename({df.columns[-1]: 'Values'}, axis=1, inplace=True)
+        df['Key'] = df['Key'].str.replace('/', '')
+        df['Key'] = df['Key'].str.replace(' ', '')
+        df.to_csv('/home/ubuntu/AI/InvoiceParser/final.csv', index=False)
+        import pandas as pd
+        x1 = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/finalwithcolen.csv')
+        merge = pd.merge(x1, tp, on='Key', how='right')
+        merge1 = merge
+        merge = merge['Values'].str.split(":", expand=True)
+        merge.rename({merge.columns[-1]: 'Values'}, axis=1, inplace=True)
+        frames = [merge1['Key'], merge['Values']]
+        result = pd.concat(frames, axis=1)
+
+        x1 = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/finalwithoutcolen.csv')
+        merged = pd.merge(x1, tp, on='Key', how='right')
+        frames = [result, merged]
+        result1 = pd.concat(frames)
+        result1.to_csv('/home/ubuntu/AI/InvoiceParser/final1.csv', index=False)
+
+        x1 = pd.read_csv('/home/ubuntu/AI/InvoiceParser/main.csv')
+        tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final1.csv')
+        tp['Key'] = tp['Key'].str.strip()
+        tp['Values'] = tp['Values'].str.strip()
+
+        merge = pd.merge(tp, x1, on='Key', how='right')
+        merge.to_csv('/home/ubuntu/AI/InvoiceParser/invoicewithouttable.csv', index=False)
+        df2 = pd.read_csv('/home/ubuntu/AI/InvoiceParser/invoicewithouttable.csv')
+
+        # Import writer class from csv module
+        from csv import writer
+
+
+        List=['PlantCode'," "]
+        with open('/home/ubuntu/AI/InvoiceParser/invoicewithouttable.csv', 'a') as f_object:
+            writer_object = writer(f_object)
+            writer_object.writerow(List)
+            f_object.close()
+        # print(df2)
+        df2 = pd.read_csv('/home/ubuntu/AI/InvoiceParser/invoicewithouttable.csv')
+        df2 = df2.T
+
+        df2.to_csv('/home/ubuntu/AI/InvoiceParser/invoicewithouttable.csv', index=False, header=False)
+
+        df1 = pd.read_csv('/home/ubuntu/AI/InvoiceParser/invoicewithouttable.csv')
+        df1.to_json('/home/ubuntu/AI/InvoiceParser/firstjson.json', orient="index")
+        import pandas as pd
+        x = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/item1.csv')
+        x['Values'] = x['Values'].str.strip()
+        merge = pd.merge(tp, x, on='Key', how='inner')
+        merge = merge.groupby('Key').agg({
+            'Values': '/'.join,
+        }).reset_index()
+        z = merge['Values'].str.split('/', expand=True)
+        frames = [merge, z]
+        result1 = pd.concat(frames, axis=1)
+        result1 = result1.drop(['Values'], axis=1)
+        import pandas as pd
+        tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/item1.csv')
+        merge = pd.merge(tp, result1, on='Key', how='inner')
+        merge = merge.T
+        new_header = merge.iloc[0]  # grab the first row for the header
+        merge = merge[1:]  # take the data less the header row
+        merge.columns = new_header
+    
+        merge = merge.to_dict('records')
+        invoice_Item=merge
+
+
+        # import pandas as pd
+        # import json
+        # dflist = []
+        # x = pd.read_csv('/home/ubuntu/AI/InvoiceParser/item1.csv')
+        # tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        # tp['Key']=tp['Key'].str.strip()
+        # tp['Values']=tp['Values'].str.strip()
+        # # tp = tp.loc[:, ~tp.columns.str.contains('^Unnamed')]
+        # merge = pd.merge(x, tp, on='Key', how='left')
+        # merge.to_csv('/home/ubuntu/AI/InvoiceParser/invoicewithtable1.csv', index=False)
+
+        # dfPG = pd.read_csv('/home/ubuntu/AI/InvoiceParser/invoicewithtable1.csv')
+        # import numpy as np
+        # dfPG = dfPG.replace({np.nan: None})
+        # x2 = dfPG.iloc[:, -2].tolist()
+        # y2 = dfPG.iloc[:, -1].tolist()
+        # z1 = dict(zip(x2, y2))
+        # dflist.append(z1)
+        # # u1 = json.dumps(z1)
+        # import pandas as pd
+
+        # x = pd.read_csv('/home/ubuntu/AI/InvoiceParser/item2.csv')
+        # tp = pd.read_csv('/home/ubuntu/AI/InvoiceParser/final.csv')
+        # tp['Key']=tp['Key'].str.strip()
+        # tp['Values']=tp['Values'].str.strip()
+        # # tp = tp.loc[:, ~tp.columns.str.contains('^Unnamed')]
+        # merge = pd.merge(x, tp, on='Key', how='left')
+        # merge.to_csv('/home/ubuntu/AI/InvoiceParser/invoicewithtable2.csv', index=False)
+
+        # dfUG = pd.read_csv('/home/ubuntu/AI/InvoiceParser/invoicewithtable2.csv')
+        # import numpy as np
+        # dfUG = dfUG.replace({np.nan: None})
+        # x2 = dfUG.iloc[:, -2].tolist()
+        # y2 = dfUG.iloc[:, -1].tolist()
+        # z2 = dict(zip(x2, y2))
+        # dflist.append(z2)
+        # u2 = json.dumps(z2)
+        # final = '[' + str(z1) + ',' + str(z2) + ']'
+        # return render_template('resume.html')
+        ############################################Document############################################################
+
+        import base64
+        empty = []
+        name = found
+        image = open(name, 'rb')
+        image_read = image.read()
+        image_64_encode = base64.b64encode(image_read)
+        NULL = 'null'
+        # empty.append("ByteData--" + (NULL).strip('""'))
+        image_64_encode = image_64_encode.decode('utf-8')
+        empty.append("FileData--" + str(image_64_encode))
+        imagedata = name.split("/")
+        imagename = str(imagedata[-1]).replace('"', '').replace("[", "").replace("]", "")
+        imagename1 = str(imagename).split('.')
+
+        imagename = str(imagename1[-2]).replace("[", "]")
+        empty.append("FileName--" + imagename)
+        empty.append("FilePath--" + name)
+        imageExtension = str(imagename1[-1]).replace("[", "]")
+        empty.append("FileType--" + imageExtension)
+
+        import pandas as pd
+        df = pd.DataFrame(empty)
+        df = df[0].str.split("--", expand=True)
+        data1 = pd.DataFrame(df[0])
+        data2 = pd.DataFrame(df[1])
+        dt = data2.set_index(data1[0])
+
+        dt4 = dt.T
+        list = []
+        dictionary = dt4.to_dict(orient="index")
+
+        a = {
+            "FileId": 0,
+            "FileData": "",
+            "FileName": "",
+            "FileType": "",
+            "RefId": 0
+        }
+        list = []
+
+        list.append(a)
+        list.append(dictionary[1])
+
+        import json
+
+        with open('/home/ubuntu/AI/InvoiceParser/firstjson.json', 'r') as json_file:
+            json_load = json.load(json_file)
+
+            # url = "https://test.bizgaze.app:8443/apis/v4/bizgaze/integrations/businesscards/create"
+
+        nothing = json.dumps(json_load).replace("]", "").replace("[", "").replace('{"0":', '').replace('}}', '}')
+        import json
+
+        # JSON data:
+        x = nothing
+
+        # python object to be appended
+        y = {"InvoiceItems":invoice_Item}
+        y1 = {"Document": list}
+
+        # parsing JSON string:
+        z = json.loads(x)
+
+        # appending the data
+        z.update(y)
+        z.update(y1)
+
+        # the result is a JSON string:
+        # print(json.dumps(z))
+        # print('##########################')
+        # print(z)
+        # print('##########################')
+        import requests
+        import json
+
+        # with open('visitingcard1.json', 'r') as json_file:
+        #     json_load = json.load(json_file)
+        url = "https://test.bizgaze.app:8443/apis/v4/bizgaze/integrations/invoice/createsalesinvoice"
+        #url="https://test.bizgaze.app:8443/apis/v4/bizgaze/integrations/invoice/createsalesinvoice"
+        payload1 = json.dumps(z)
+        print('--------------------------------------------------------------------------')
+        print(payload1)
+        headers = {
+            'Authorization': 'stat 089166c35d4c4d7d941c99d6f8986834',
+            'Content-Type': 'application/json'
+        }
+        response = requests.request("POST", url, headers=headers, data=payload1)
+        print("##############################################################")
+        print(response.text)
+
+        import glob
+        files = glob.glob(
+            "/home/ubuntu/AI/InvoiceParser/upload_invoice/*"
+        )
+        for f in files:
+            os.remove(f)
+        files = glob.glob(
+            "/home/ubuntu/AI/InvoiceParser/uploads/*"
+        )
+        for f in files:
+            os.remove(f)
+
+        return payload1
+
+
+@app.route("/Download_invoice")
+def Download_invoice():
+    pass
+   
+
+@app.route("/Table")
+def Table():
+    pass
+
+
+
+@app.route('/upload_invoice', methods=["POST"])
+def upload_invoice():
+    if __name__ == "__main__":
+        url_list = []
+        Dataset = request.get_json()
+        # id = "100013660000125"
+        url_list.append(Dataset)
+        # multiprocessing
+        with multiprocessing.Pool(processes=30) as pool:
+            results = pool.map(predict, url_list)
+
+        pool.close()
+        return results[0]
+
+
+if __name__ == "__main__":
+    app.run(host='0.0.0.0', port=9797, debug=True)

Invoice_parser/invoicewithouttable.csv

@@ -0,0 +1,2 @@
+SELLER NAME,SELLER ADDRESS,SELLER PH,SELLER EMAIL,SELLER GST,SELLER PAN,BUYER NAME,BUYER ADDRESS,BUYER GST,INVOICE NO,INVOICE DATE,SHIP TO,SHIP TO CONTACT,DESTINATION,TOTAL PACKS & QUANTITY,ASSESSABLE AMOUNT,AMOUNT IN WORDS,PAYMENT ON OR BEFORE,OUTPUT SGST,OUTPUT CGST,ROUND OFF,RTS POINTS EARNED,OVERALL RTS POINTS,GRAND TOTAL,OUR BANK DETAILS,BANK A/C NO,RTGS/IFSC
+Seller : SHREE TRADING CORPORATION,"H- 575A,ROAD NO.6, V.K.I AREA, Jaipur, Rajasthan - 302023",Phone: 9610566688,Email : stc.jaipur@gmail.com,GST No. : 08AAVPM5307P1ZV,PAN No. : AAVPM5307P,Buyer : Stonex India Pvt. Ltd.,"Khasra No. 210, Village - Rahimpura,Makrana Road Kishangarh, 305801",GST No. :08AACCG9620R1ZZ,Invoice No. : JPR21-22/XM01902,Date : 28 Jul 2021,Ship to : ,"Contact: Rajat Ji,9116616323",Destination Kishangarh,Total Quantity 2.00 416.00,Assessable Amount 87360.00,Amount in words : Rupees One Lakh Three Thousand Eighty Five only,Payment on or before Save To pay,Output SGST  ,7862.40 Output CGST  ,Round off 0.20,,,Grand Total 103085.00,Our Bank Details : Kotak Mahindra Bank,Bank A/c No. : 1412405384,RTGS / IFSC Code : KKBK0003540

Invoice_parser/invoicewithtable1.csv

@@ -0,0 +1,10 @@
+Key,Values
+SI,1
+HSN,27101980
+PRODUCT,"MOBILGEAR 600 XP 680, 208LT, DR-"
+PACK SIZE,1.00
+QUANTITY,208.00 LTR
+RATE,240.00
+DISC,0.000
+TAX %,9%|9%
+AMOUNT,49920.00

Invoice_parser/invoicewithtable2.csv

@@ -0,0 +1,10 @@
+Key,Implement,Values
+SI_1,SI,2
+HSN_1,HSN,27101980
+PRODUCT_1,PRODUCT,SPARTAN EP 150 DRUM 208L:IN-     
+PACK SIZE_1,PACK SIZE,1.00
+QUANTITY_1,QUANTITY,208.00 LTR
+RATE_1,RATE,180.00
+DISC_1,DISC,0.000
+TAX %_1,TAX %,9%|9%
+AMOUNT_1,AMOUNT,37440.00

Invoice_parser/item1.csv

@@ -0,0 +1,10 @@
+Key
+SI
+HSN
+PRODUCT
+PACKSIZE
+QUANTITY
+RATE
+DISC
+TAX %
+AMOUNT

Invoice_parser/item2.csv

@@ -0,0 +1,10 @@
+Key,Implement
+SI_1,SI
+HSN_1,HSN
+PRODUCT_1,PRODUCT
+PACK SIZE_1,PACK SIZE
+QUANTITY_1,QUANTITY
+RATE_1,RATE
+DISC_1,DISC
+TAX %_1,TAX %
+AMOUNT_1,AMOUNT

Invoice_parser/main.csv

@@ -0,0 +1,28 @@
+Key
+SELLER NAME
+SELLER ADDRESS
+SELLER PH
+SELLER EMAIL
+SELLER GST
+SELLER PAN
+BUYER NAME
+BUYER ADDRESS
+BUYER GST
+INVOICE NO
+INVOICE DATE
+SHIP TO
+SHIP TO CONTACT
+DESTINATION
+TOTAL PACKS & QUANTITY
+ASSESSABLE AMOUNT
+AMOUNT IN WORDS
+PAYMENT ON OR BEFORE
+OUTPUT SGST
+OUTPUT CGST
+ROUND OFF
+RTS POINTS EARNED
+OVERALL RTS POINTS
+GRAND TOTAL
+OUR BANK DETAILS
+BANK A/C NO
+RTGS/IFSC

Invoice_parser/p/meta.json

@@ -0,0 +1 @@
+{"lang":"en","name":"model","version":"0.0.0","spacy_version":">=2.2.4","description":"","author":"","email":"","url":"","license":"","vectors":{"width":0,"vectors":0,"keys":0,"name":"spacy_pretrained_vectors"},"pipeline":["ner"],"factories":{"ner":"ner"},"labels":{"ner":["AMOUNT","AMOUNT IN WORDS","ASSESSABLE AMOUNT","BANK A/C NO","BUYER ADDRESS","BUYER GST","BUYER NAME","BUYER PAN","DESTINATION","DISC","DISPATCHED THROUGH","GRAND TOTAL","HSN","INVOICE DATE","INVOICE NO","NARRATION","OUR BANK DETAILS","OUTPUT CGST","OUTPUT SGST","OVERALL RTS POINTS","Output IGST","PACK SIZE","PAYMENT ON OR BEFORE","PAYMENT TYPE","PAYMENT TYPE ","PO NO","PRODUCT","QUANTITY","RATE","ROUND OFF","RTGS/IFSC","RTGS/IFSC ","RTS POINTS EARNED","SELLER ADDRESS","SELLER EMAIL","SELLER GST","SELLER NAME","SELLER PAN","SELLER PH","SHIP TO","SHIP TO ADDRESS","SHIP TO CONTACT","SHIP TO GST","SI","TAX %","TOTAL PACKS & QUANTITY","TOTAL PACKS AND QUANTITY"]}}

Invoice_parser/p/ner/cfg

@@ -0,0 +1,18 @@
+{
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":1.0,
+  "cnn_maxout_pieces":3,
+  "nr_feature_tokens":6,
+  "nr_class":190,
+  "hidden_depth":1,
+  "token_vector_width":96,
+  "hidden_width":64,
+  "maxout_pieces":2,
+  "pretrained_vectors":null,
+  "bilstm_depth":0,
+  "self_attn_depth":0,
+  "conv_depth":4,
+  "conv_window":1,
+  "embed_size":2000
+}

Invoice_parser/p/ner/moves

@@ -0,0 +1 @@
+�¥movesÚ

Invoice_parser/p/vocab/key2row

@@ -0,0 +1 @@
+�

Invoice_parser/requirementsinvoice.txt

@@ -0,0 +1,87 @@
+asgiref==3.5.0
+backports.zoneinfo==0.2.1
+blis==0.7.5
+camelot-py==0.10.1
+catalogue==1.0.0
+certifi==2021.10.8
+cffi==1.15.0
+chardet==4.0.0
+charset-normalizer==2.0.9
+ci-info==0.2.0
+click==8.0.3
+coloredlogs==15.0.1
+configobj==5.0.6
+configparser==5.2.0
+cryptography==36.0.1
+cycler==0.11.0
+cymem==2.0.6
+Django==4.0.3
+docx==0.2.4
+docx2txt==0.8
+et-xmlfile==1.1.0
+etelemetry==0.2.2
+filelock==3.4.2
+fitz==0.0.1.dev2
+Flask==2.0.2
+fonttools==4.28.5
+future==0.18.2
+ghostscript==0.7
+httplib2==0.20.2
+humanfriendly==10.0
+idna==3.3
+image==1.5.33
+img2pdf==0.4.3
+importlib-resources==5.4.0
+isodate==0.6.1
+itsdangerous==2.0.1
+Jinja2==3.0.3
+kiwisolver==1.3.2
+lxml==4.7.1
+MarkupSafe==2.0.1
+matplotlib==3.5.1
+murmurhash==1.0.6
+networkx==2.6.3
+nibabel==3.2.1
+nipype==1.7.0
+numpy==1.22.0
+ocrmypdf==13.4.1
+opencv-python==4.5.5.62
+openpyxl==3.0.9
+packaging==21.3
+pandas==1.3.5
+pathlib==1.0.1
+pdfminer.six==20211012
+pikepdf==5.1.0
+Pillow==9.0.0
+plac==1.1.3
+pluggy==1.0.0
+preshed==3.0.6
+prov==2.0.0
+pycparser==2.21
+pydot==1.4.2
+PyMuPDF==1.19.4
+pyparsing==3.0.6
+PyPDF2==1.26.0
+pytesseract==0.3.8
+python-dateutil==2.8.2
+python-docx==0.8.11
+pytz==2021.3
+pyxnat==1.4
+rdflib==6.1.1
+reportlab==3.6.8
+requests==2.26.0
+scipy==1.7.3
+simplejson==3.17.6
+six==1.16.0
+spacy==2.3.5
+sqlparse==0.4.2
+srsly==1.0.5
+tabulate==0.8.9
+thinc==7.4.5
+tqdm==4.62.3
+traits==6.3.2
+urllib3==1.26.7
+wasabi==0.9.0
+Werkzeug==2.0.2
+xlrd==1.2.0
+zipp==3.7.0

Invoice_parser/templates/Error.html

@@ -0,0 +1,92 @@
+
+<html>
+<head>
+
+<style>
+
+.button {
+  background-color: #000000; /* Green */
+  border: none;
+  color: white;
+  padding: 15px 32px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  margin: 4px 2px;
+  cursor: pointer;
+}
+
+
+.button1 {font-size: 10px;}
+.button2 {font-size: 12px;}
+.button3 {font-size: 16px;}
+.button4 {font-size: 50px;}
+.button5 {font-size: 24px;border-radius: 12px;}
+
+ body {
+	width: 100%;
+	height:100%;
+	font-family: 'Helvetica';
+	background-color:#000000;
+	color: #fff;
+	font-size: 24px;
+	text-align:center;
+	letter-spacing:1.4px;
+	}
+.dropbtn {
+  background-color: #04AA6D;
+  color: white;
+  padding: 16px;
+  font-size: 16px;
+  border: none;
+}
+
+.dropdown {
+  position: relative;
+  display: inline-block;
+}
+
+.dropdown-content {
+  display: none;
+  position: absolute;
+  background-color: #f1f1f1;
+  min-width: 160px;
+  box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2);
+  z-index: 1;
+}
+
+.dropdown-content a {
+  color: black;
+  padding: 12px 16px;
+  text-decoration: none;
+  display: block;
+}
+
+.dropdown-content a:hover {background-color: #ddd;}
+
+.dropdown:hover .dropdown-content {display: block;}
+
+.dropdown:hover .dropbtn {background-color: #3e8e41;}
+</style>
+</head>
+<body>
+<div style="background-image: url('https://lh3.googleusercontent.com/p/AF1QipONWF8G50u9Bu-dklcj3kzesofOn8Z0q0LdHeU1=w1080-h608-p-no-v0');
+   /* Full height */
+  height: 100%;
+    / Center and scale the image nicely /
+  background-position: center;
+  background-repeat: no-repeat;
+  background-size: cover;">
+<br>
+<br>
+  <br>
+  <br>
+    <br>  <br>
+      <a  class="button button5"href="/">RETURN HOME</a><br><br><br>
+      
+	<h3 class="button button3">Invalid File Input </h3>
+  </div>
+</div>
+
+</body>
+</html>

Invoice_parser/templates/home.html

@@ -0,0 +1,97 @@
+
+<html>
+<head>
+
+<style>
+
+.button {
+  background-color: #000000; /* Green */
+  border: none;
+  color: white;
+  padding: 15px 32px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  margin: 4px 2px;
+  cursor: pointer;
+}
+
+
+.button1 {font-size: 10px;}
+.button2 {font-size: 12px;}
+.button3 {font-size: 16px;}
+.button4 {font-size: 50px;}
+.button5 {font-size: 24px;border-radius: 12px;}
+
+ body {
+	width: 100%;
+	height:100%;
+	font-family: 'Helvetica';
+	background-color:#000000;
+	color: #fff;
+	font-size: 24px;
+	text-align:center;
+	letter-spacing:1.4px;
+	}
+.dropbtn {
+  background-color: #04AA6D;
+  color: white;
+  padding: 16px;
+  font-size: 16px;
+  border: none;
+}
+
+.dropdown {
+  position: relative;
+  display: inline-block;
+}
+
+.dropdown-content {
+  display: none;
+  position: absolute;
+  background-color: #f1f1f1;
+  min-width: 160px;
+  box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2);
+  z-index: 1;
+}
+
+.dropdown-content a {
+  color: black;
+  padding: 12px 16px;
+  text-decoration: none;
+  display: block;
+}
+
+.dropdown-content a:hover {background-color: #ddd;}
+
+.dropdown:hover .dropdown-content {display: block;}
+
+.dropdown:hover .dropbtn {background-color: #3e8e41;}
+</style>
+</head>
+<body>
+<div style="background-image: url('https://lh3.googleusercontent.com/p/AF1QipONWF8G50u9Bu-dklcj3kzesofOn8Z0q0LdHeU1=w1080-h608-p-no-v0');
+   /* Full height */
+  height: 100%;
+    / Center and scale the image nicely /
+  background-position: center;
+  background-repeat: no-repeat;
+  background-size: cover;">
+<br>
+<br>
+  <br>
+<h2 class="button button5">Bizgaze Limited</h2><br>
+  <br>
+
+
+<div class="dropdown">
+  <button class="button button5" >Parser</button>
+  <div class="dropdown-content">
+    <a href="/resume">  RESUME  </a>
+    <a href="/invoice">  INVOICE  </a>
+
+  </div>
+</div>
+
+</body>
+</html>

Invoice_parser/templates/invoice.html

@@ -0,0 +1,85 @@
+<html>
+
+<head>
+    <style>
+.button {
+  background-color: #000000; /* Green */
+  border: none;
+  color: white;
+  padding: 15px 32px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  margin: 4px 2px;
+  cursor: pointer;
+}
+
+
+.button1 {font-size: 10px;}
+.button2 {font-size: 12px;}
+.button3 {font-size: 16px;}
+.button4 {font-size: 50px;}
+.button5 {font-size: 24px;border-radius: 12px;}
+
+</style>
+
+</head>
+
+<body>
+<div style="background-image: url('https://lh3.googleusercontent.com/p/AF1QipONWF8G50u9Bu-dklcj3kzesofOn8Z0q0LdHeU1=w1080-h608-p-no-v0');
+   /* Full height */
+  height: 100%;
+    / Center and scale the image nicely /
+  background-position: center;
+  background-repeat: no-repeat;
+  background-size: cover;">
+
+      <h1 class="button button5"> INVOICE PARSER </h1>
+
+    <br>  <br>
+      <a  class="button button5"href="/">HOME</a>
+
+
+
+<form action="/upload_invoice" method="POST" enctype="multipart/form-data">
+        <div class="form-group">
+
+
+          <div class="custom-file">
+            <input type="file" class="button button5" name="image" id="image" accept=".jpg,.png,.jpeg,.JPEG,.pdf"> <br> <br><br>
+<div class="bg"></div>
+  <input class="button button5" type="submit">
+
+          </div>
+        </div>
+    </form>
+   <form action="{{ url_for('Download_invoice') }}" method="GET">
+       <br><br>  <input type="submit" class="button button5" value="Download"></form>
+      <form action="{{ url_for('Table') }}" method="GET">
+       <br><br>  <input type="submit" class="button button5" value="Table"></form>
+
+
+
+
+
+
+
+<style>
+
+   body {
+	width: 100%;
+	height:100%;
+	font-family: 'Helvetica';
+	background-color:#000000;
+	color: #fff;
+	font-size: 24px;
+	text-align:center;
+	letter-spacing:1.4px;
+
+}
+  </style>
+
+
+
+</body>
+</html>

Invoice_parser/templates/resume.html

@@ -0,0 +1,82 @@
+<html>
+
+<head>
+    <style>
+.button {
+  background-color: #000000; /* Green */
+  border: none;
+  color: white;
+  padding: 15px 32px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  margin: 4px 2px;
+  cursor: pointer;
+}
+
+
+.button1 {font-size: 10px;}
+.button2 {font-size: 12px;}
+.button3 {font-size: 16px;}
+.button4 {font-size: 50px;}
+.button5 {font-size: 24px;border-radius: 12px;}
+
+</style>
+
+</head>
+
+<body>
+<div style="background-image: url('https://lh3.googleusercontent.com/p/AF1QipONWF8G50u9Bu-dklcj3kzesofOn8Z0q0LdHeU1=w1080-h608-p-no-v0');
+   /* Full height */
+  height: 100%;
+    / Center and scale the image nicely /
+  background-position: center;
+  background-repeat: no-repeat;
+  background-size: cover;">
+
+      <h1 class="button button5"> RESUME PARSER </h1>
+    <br>  <br>
+    <a  class="button button5"href="/">HOME</a>
+
+
+
+<form action="/upload_resume" method="POST" enctype="multipart/form-data">
+        <div class="form-group">
+
+
+          <div class="custom-file">
+            <input type="file" class="button button5" name="image" id="image" accept=".doc,.docx,.pdf"> <br> <br><br>
+<div class="bg"></div>
+  <input class="button button5" type="submit">
+
+          </div>
+        </div>
+    </form>
+   <form action="{{ url_for('Download_resume') }}" method="GET">
+       <br><br>  <input type="submit" class="button button5" value="Download"></form>
+
+
+
+
+
+
+
+<style>
+
+   body {
+	width: 100%;
+	height:100%;
+	font-family: 'Helvetica';
+	background-color:#000000;
+	color: #fff;
+	font-size: 24px;
+	text-align:center;
+	letter-spacing:1.4px;
+
+}
+  </style>
+
+
+
+</body>
+</html>